mirror of
https://github.com/wassname/llm-moral-foundations2.git
synced 2026-08-16 11:23:03 +08:00
911a4c31e0730e1b80c760ef3846ed6c5fc856ae
Unbiased Assessment of LLM Moral Foundations: Controlling for Positional Effects and Response Steering
Difference from previous work
- control for positional bias
- use mechinterp representation steering
Links:
Languages
Jupyter Notebook
99.3%
Python
0.7%